[R] Linear Regression with Linear Equality Constraint

[Comcast]

On Oct 31, 2011, at 3:31 PM, Bert Gunter <gunter.berton at gene.com> wrote:

> Well, if I understand the question correctly (following the posting guide
> would have spared guessing, as usual), forget packages -- nothing more than
> elementary algebra is needed.
> 
> e.g.
> 
> lm(y ~ x1 + x2 + x3)  subject to the constraint beta_2 = beta_3, the
> coefficients of x2 and x3, is the same as
> 
> lm (y ~ x1 + z)   where z = x3 + x3 (sum of the 2 covariate vectors).
> 

I would have expected to divide the beta_z by 2 to get the beta2 = beta3. Did I  over-think this?

-- 
David
> etc. etc.   ...  ???
> 
> -- Bert
> 
> On Mon, Oct 31, 2011 at 12:16 PM, Kristian Lind <
> kristian.langgaard.lind at gmail.com> wrote:
> 
>> I believe the package systemfit can help you with that. Haven't tried it
>> myself, but give it a go.
>> 
>> Regards,
>> 
>> Kristian
>> 
>> 2011/10/31 JW <jon at phatrasecurities.com>
>> 
>>> Please advice on the package I should use to run a linear regression
>> model
>>> (weighted least squared) with linear equality constraint.  I initially
>>> tried
>>> "constrOptim" but it turned out that it only supported inequality linear
>>> constraint.  Thank you very much in advance.
>>> 
>>> Cheers,
>>> 
>>> Jon
>>> 
>>> --
>>> View this message in context:
>>> 
>> http://r.789695.n4.nabble.com/Linear-Regression-with-Linear-Equality-Constraint-tp3956588p3956588.html
>>> Sent from the R help mailing list archive at Nabble.com.
>>> 
>>> ______________________________________________
>>> R-help at r-project.org mailing list
>>> https://stat.ethz.ch/mailman/listinfo/r-help
>>> PLEASE do read the posting guide
>>> http://www.R-project.org/posting-guide.html
>>> and provide commented, minimal, self-contained, reproducible code.
>>> 
>> 
>>       [[alternative HTML version deleted]]
>> 
>> ______________________________________________
>> R-help at r-project.org mailing list
>> https://stat.ethz.ch/mailman/listinfo/r-help
>> PLEASE do read the posting guide
>> http://www.R-project.org/posting-guide.html
>> and provide commented, minimal, self-contained, reproducible code.
>> 
> 
> 
> 
> -- 
> 
> Bert Gunter
> Genentech Nonclinical Biostatistics
> 
> Internal Contact Info:
> Phone: 467-7374
> Website:
> http://pharmadevelopment.roche.com/index/pdb/pdb-functional-groups/pdb-biostatistics/pdb-ncb-home.htm
> 
>    [[alternative HTML version deleted]]
> 
> ______________________________________________
> R-help at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.